{ "bcoid": "GLY_000024", "title": "Human Cancer Mutation", "description": "The Human Cancer Mutation dataset contains human [taxid:9606] mutation data from BioMuta database (https://hive.biochemistry.gwu.edu/biomuta). ", "filename": "human_protein_mutation_cancer.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Somatic Cancer Mutations", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q08AF3-1...", "468..." ], [ "P30711-1...", "188..." ] ], "headers": [ "uniprotkb_ca...", "aa_pos..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "aa_pos" }, { "type": "string", "label": "ref_aa" }, { "type": "string", "label": "alt_aa" }, { "type": "string", "label": "chr_id" }, { "type": "string", "label": "chr_pos" }, { "type": "string", "label": "ref_nt" }, { "type": "string", "label": "alt_nt" }, { "type": "string", "label": "patients_positive" }, { "type": "string", "label": "patients_tested" }, { "type": "string", "label": "mut_freq" }, { "type": "string", "label": "data_source" }, { "type": "string", "label": "do_id" }, { "type": "string", "label": "do_name" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "filter_flags" }, { "type": "string", "label": "glyco_annotation" }, { "type": "string", "label": "mim_id" }, { "type": "string", "label": "somatic_status" }, { "type": "string", "label": "minor_allelic_frequency" } ], [ "Q08AF3-1", "468", "M", "L", "17", "33591465", "A", "T", "1", "50", "2.0", "icgc", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "Q08AF3", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P30711-1", "188", "R", "P", "22", "24376583", "C", "G", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "P30711", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O95907-1", "69", "Y", "*", "22", "38478674", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "O95907", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8IZV5-1", "47", "G", "D", "8", "74207664", "G", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q8IZV5", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q5T5N4-1", "212", "A", "T", "6", "165715177", "C", "T", "1", "456", "0.2", "tcga", "9256", "DOID:9256 / colorectal cancer", "protein_xref_biomuta", "Q5T5N4", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs201539458.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O14646-1", "462", "R", "M", "5", "98233005", "C", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "O14646", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O60291-1", "78", "H", "Q", "16", "4701990", "C", "G", "1", "66", "1.5", "icgc", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "O60291", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.5%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9UPZ3-1", "223", "F", "V", "11", "18327839", "A", "C", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q9UPZ3", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O60486-1", "1175", "V", "E", "12", "94658928", "T", "A", "1", "25", "4.0", "icgc", "10283", "DOID:10283 / prostate cancer", "protein_xref_biomuta", "O60486", "Somatic mutation passed 1 out of 6 filters: patient freq. (4.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q96RT1-1", "264", "S", "P", "5", "65320251", "T", "C", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q96RT1", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O00160-1", "644", "R", "W", "19", "8601249", "G", "A", "1", "558", "0.2", "tcga", "363", "DOID:363 / uterine cancer", "protein_xref_biomuta", "O00160", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "A6NJZ7-1", "1273", "S", "G", "22", "21901449", "T", "C", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "A6NJZ7", "Somatic mutation passed 2 out of 6 filters: patient freq. (1.0%); num. of cancers (3). In dbSNP: rs1337913321.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q6PIZ9-1", "179", "R", "H", "3", "108572699", "G", "A", "1", "162", "0.6", "tcga", "9256", "DOID:9256 / colorectal cancer", "protein_xref_biomuta", "Q6PIZ9", "Somatic mutation passed 1 out of 6 filters: num. of cancers (4). In dbSNP: rs79029897.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P05787-1", "37", "S", "C", "12", "53298657", "T", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "P05787", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q96AQ1-1", "122", "G", "R", "2", "132288220", "G", "A", "1", "820", "0.1", "tcga", "4159", "DOID:4159 / skin cancer", "protein_xref_biomuta", "Q96AQ1", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P01588-1", "166", "R", "H", "7", "100320671", "G", "A", "1", "399", "0.3", "tcga", "1793", "DOID:1793 / pancreatic cancer", "protein_xref_biomuta", "P01588", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8N5T2-1", "100", "S", "I", "4", "26638837", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q8N5T2", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q96C55-1", "28", "P", "H", "19", "56113561", "C", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q96C55", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P17017-1", "603", "R", "*", "19", "19822283", "G", "A", "3", "558", "0.5", "tcga", "363", "DOID:363 / uterine cancer", "protein_xref_biomuta", "P17017", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs757216310.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q6ZWE6-1", "79", "R", "K", "2", "208866128", "C", "T", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q6ZWE6", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q96M86-3", "1772", "R", "Q", "11", "6567484", "G", "A", "1", "48", "2.1", "tcga", "2531", "DOID:2531 / hematologic cancer", "protein_xref_biomuta", "Q96M86", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.1%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9Y5I1-1", "620", "P", "T", "5", "140250546", "C", "A", "1", "72", "1.4", "icgc", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "Q9Y5I1", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.4%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q5T1V6-1", "111", "C", "W", "1", "200635536", "A", "C", "1", "94", "1.1", "icgc", "9256", "DOID:9256 / colorectal cancer", "protein_xref_biomuta", "Q5T1V6", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.1%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q86XP6-1", "83", "I", "M", "2", "69174345", "G", "C", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q86XP6", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%). In dbSNP: rs1001718385.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q13233-1", "1383", "R", "K", "5", "56183238", "G", "A", "1", "25", "4.0", "icgc", "10283", "DOID:10283 / prostate cancer", "protein_xref_biomuta", "Q13233", "Somatic mutation passed 1 out of 6 filters: patient freq. (4.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P23526-1", "68", "V", "I", "20", "32883218", "C", "T", "1", "456", "0.2", "tcga", "9256", "DOID:9256 / colorectal cancer", "protein_xref_biomuta", "P23526", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs199533546.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q14194-1", "16", "R", "*", "4", "5868477", "G", "A", "1", "48", "2.1", "tcga", "2531", "DOID:2531 / hematologic cancer", "protein_xref_biomuta", "Q14194", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.1%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P0C7Q6-1", "105", "Y", "C", "17", "7385617", "A", "G", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "P0C7Q6", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q6ZQQ6-1", "2141", "R", "W", "19", "38377773", "G", "A", "1", "254", "0.4", "icgc", "9256", "DOID:9256 / colorectal cancer", "protein_xref_biomuta", "Q6ZQQ6", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q66K14-1", "939", "S", "*", "5", "179294825", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q66K14", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8N7X1-1", "52", "A", "T", "X", "114424158", "G", "A", "1", "558", "0.2", "tcga", "363", "DOID:363 / uterine cancer", "protein_xref_biomuta", "Q8N7X1", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8NGE9-1", "248", "V", "I", "11", "57958704", "G", "A", "1", "1514", "0.1", "tcga", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "Q8NGE9", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q86SZ2-1", "100", "R", "H", "14", "39623467", "C", "T", "1", "1118", "0.1", "tcga", "10283", "DOID:10283 / prostate cancer", "protein_xref_biomuta", "Q86SZ2", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs763991701.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q96LP2-1", "368", "Q", "E", "5", "94784045", "C", "G", "1", "1514", "0.1", "tcga", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "Q96LP2", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9Y4F9-1", "233", "R", "W", "6", "24850926", "G", "A", "1", "678", "0.1", "tcga", "1319", "DOID:1319 / brain cancer", "protein_xref_biomuta", "Q9Y4F9", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs753095324.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q7LGC8-1", "189", "R", "H", "10", "73767355", "G", "A", "1", "72", "1.4", "icgc", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "Q7LGC8", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.4%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q6DHY5-1", "507", "A", "T", "17", "34797617", "C", "T", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q6DHY5", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9H5Z1-1", "554", "A", "S", "20", "37652399", "G", "T", "1", "66", "1.5", "icgc", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "Q9H5Z1", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.5%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q05639-1", "418", "Y", "S", "20", "62120282", "T", "G", "1", "350", "0.3", "tcga", "4362", "DOID:4362 / cervical cancer", "protein_xref_biomuta", "Q05639", "Somatic mutation passed 1 out of 6 filters: num. of cancers (10).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P06331-1", "5", "H", "L", "14", "106830032", "T", "A", "1", "38", "2.6", "icgc", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "P06331", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.6%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P12882-1", "1568", "E", "A", "17", "10399820", "T", "G", "2", "191", "1.0", "tcga", "5041", "DOID:5041 / esophageal cancer", "protein_xref_biomuta", "P12882", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O14495-1", "153", "R", "C", "1", "56990067", "G", "A", "1", "399", "0.3", "tcga", "1793", "DOID:1793 / pancreatic cancer", "protein_xref_biomuta", "O14495", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs749957963.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P35222-1", "41", "T", "A", "3", "41266124", "A", "G", "3", "1118", "0.3", "tcga", "10283", "DOID:10283 / prostate cancer", "protein_xref_biomuta", "P35222", "Somatic mutation passed 1 out of 6 filters: num. of cancers (10). In dbSNP: rs121913412.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9H6A9-1", "167", "R", "W", "11", "65385099", "C", "T", "1", "93", "1.1", "icgc", "2394", "DOID:2394 / ovarian cancer", "protein_xref_biomuta", "Q9H6A9", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.1%). In dbSNP: rs989472796.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q2M3G0-4", "1196", "H", "N", "7", "20795059", "C", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q2M3G0", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q969V6-1", "277", "Q", "H", "22", "40816901", "C", "G", "2", "820", "0.2", "tcga", "4159", "DOID:4159 / skin cancer", "protein_xref_biomuta", "Q969V6", "Somatic mutation passed 1 out of 6 filters: num. of cancers (6).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9BZF9-1", "104", "A", "D", "15", "70983693", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q9BZF9", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9Y6Y1-1", "1636", "Q", "*", "1", "7812541", "C", "T", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q9Y6Y1", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q14190-1", "280", "A", "T", "21", "38103440", "G", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q14190", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O60347-1", "732", "S", "L", "10", "96291153", "C", "T", "1", "742", "0.1", "tcga", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "O60347", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q96MG8-1", "162", "R", "Q", "8", "52746175", "C", "T", "1", "1144", "0.1", "tcga", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "Q96MG8", "Somatic mutation passed 1 out of 6 filters: num. of cancers (4).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9NQG6-1", "410", "Q", "L", "22", "39910165", "A", "T", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q9NQG6", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q13620-2", "369", "R", "Q", "X", "119678367", "C", "T", "1", "1144", "0.1", "tcga", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "Q13620", "Somatic mutation passed 1 out of 6 filters: num. of cancers (4).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P43354-1", "100", "Y", "N", "2", "157186401", "A", "T", "2", "150", "1.3", "tcga", "2531", "DOID:2531 / hematologic cancer", "protein_xref_biomuta", "P43354", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.3%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9UPV9-1", "139", "K", "N", "3", "42226230", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q9UPV9", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P50391-1", "135", "V", "M", "10", "47087186", "G", "A", "1", "678", "0.1", "tcga", "1319", "DOID:1319 / brain cancer", "protein_xref_biomuta", "P50391", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P14867-1", "421", "R", "*", "5", "161324318", "C", "T", "4", "678", "0.6", "tcga", "1319", "DOID:1319 / brain cancer", "protein_xref_biomuta", "P14867", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q14318-1", "279", "A", "E", "19", "18648517", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q14318", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P01111-1", "61", "Q", "K", "1", "115256530", "G", "T", "1", "93", "1.1", "icgc", "2394", "DOID:2394 / ovarian cancer", "protein_xref_biomuta", "P01111", "Somatic mutation passed 2 out of 6 filters: patient freq. (1.1%); num. of cancers (14). In dbSNP: rs121913254.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q13515-1", "218", "L", "F", "3", "133167414", "G", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q13515", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q7Z6G8-1", "26", "R", "W", "12", "100377940", "T", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q7Z6G8", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9UBU7-1", "462", "L", "F", "7", "87536837", "C", "T", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q9UBU7", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P38432-1", "115", "Q", "*", "17", "55028260", "G", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "P38432", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8N0X2-1", "437", "R", "C", "2", "214794778", "C", "T", "1", "742", "0.1", "tcga", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q8N0X2", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs142357329.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q5QP82-1", "8", "S", "R", "9", "37800887", "C", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q5QP82", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O43405-1", "91", "R", "Q", "14", "31348049", "G", "A", "1", "980", "0.1", "tcga", "11934", "DOID:11934 / head and neck cancer", "protein_xref_biomuta", "O43405", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "P08922-1", "1737", "E", "*", "6", "117658374", "C", "A", "1", "558", "0.2", "tcga", "363", "DOID:363 / uterine cancer", "protein_xref_biomuta", "P08922", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9UPA5-1", "2031", "R", "C", "3", "49693080", "C", "T", "1", "125", "0.8", "icgc", "2531", "DOID:2531 / hematologic cancer", "protein_xref_biomuta", "Q9UPA5", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q92731-1", "501", "R", "C", "14", "64699947", "G", "A", "30", "1514", "2.0", "tcga", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "Q92731", "Somatic mutation passed 2 out of 6 filters: patient freq. (2.0%); patient count (30/1514). In dbSNP: rs528840784.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9UBN7-1", "506", "R", "H", "X", "48674571", "G", "A", "1", "558", "0.2", "tcga", "363", "DOID:363 / uterine cancer", "protein_xref_biomuta", "Q9UBN7", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs782393826.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "A1KZ92-1", "251", "V", "I", "8", "52384808", "C", "T", "1", "1144", "0.1", "tcga", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "A1KZ92", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3). In dbSNP: rs776904737.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9UBE0-1", "78", "A", "T", "19", "47653480", "G", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q9UBE0", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q15878-1", "802", "A", "V", "1", "181701627", "C", "T", "1", "558", "0.2", "tcga", "363", "DOID:363 / uterine cancer", "protein_xref_biomuta", "Q15878", "Somatic mutation passed 1 out of 6 filters: num. of cancers (3).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q6UXN9-1", "71", "Y", "H", "3", "52304776", "A", "G", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q6UXN9", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q5TC12-1", "191", "A", "T", "1", "47118270", "C", "T", "1", "66", "1.5", "icgc", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "Q5TC12", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.5%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O95238-1", "197", "L", "P", "6", "34508805", "A", "G", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "O95238", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8NHY0-1", "510", "V", "A", "17", "47246918", "T", "C", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q8NHY0", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9H7T0-1", "155", "R", "*", "14", "92174488", "G", "A", "1", "215", "0.5", "icgc", "10283", "DOID:10283 / prostate cancer", "protein_xref_biomuta", "Q9H7T0", "Somatic mutation passed 1 out of 6 filters: num. of cancers (4). In dbSNP: rs779893104.", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q8IX15-1", "539", "D", "E", "14", "23744820", "A", "T", "1", "66", "1.5", "icgc", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "Q8IX15", "Somatic mutation passed 2 out of 6 filters: patient freq. (1.5%); num. of cancers (5).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9H114-1", "66", "R", "K", "20", "23421101", "G", "A", "1", "50", "2.0", "icgc", "1612", "DOID:1612 / breast cancer", "protein_xref_biomuta", "Q9H114", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q6IPR3-1", "174", "A", "E", "1", "75218070", "C", "A", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q6IPR3", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "O60481-1", "102", "P", "A", "X", "136649154", "C", "G", "1", "38", "2.6", "icgc", "1324", "DOID:1324 / lung cancer", "protein_xref_biomuta", "O60481", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.6%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9Y3Z3-1", "18", "S", "R", "20", "35579995", "T", "G", "1", "50", "2.0", "icgc", "1781", "DOID:1781 / thyroid cancer", "protein_xref_biomuta", "Q9Y3Z3", "Somatic mutation passed 1 out of 6 filters: patient freq. (2.0%).", "glycancount:0, pmidcount:0", "", "1", "" ], [ "Q9BSJ8-1", "53", "A", "V", "12", "56522261", "C", "T", "1", "103", "1.0", "icgc", "11054", "DOID:11054 / urinary bladder cancer", "protein_xref_biomuta", "Q9BSJ8", "Somatic mutation passed 1 out of 6 filters: patient freq. (1.0%).", "glycancount:0, pmidcount:0", "", "1", "" ] ] }, "readme": "Name\n - Human Cancer Mutation\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-01-23T17:21:05.891293\n\nModified on\n - 2022-01-12T16:00:11.801720\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@email.gwu.edu]\n\nAuthors\n - Not Applicable []\n\nChecksum\n - \n\nUsability Domain\n - The Human Cancer Mutation dataset contains human [taxid:9606] mutation data from BioMuta database (https://hive.biochemistry.gwu.edu/biomuta).\n - The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.\n - BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.\n - The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset please provide proper attribution to BioMuta and GlyGen. \n - Note the mutation shown in GlyGen are annotated based on passing of one or more filter criterias.\n - Filter criteria 1 - Positive Patient's Frequency Ratio \u2265 1.0%\n - Filter criteria 2 - Presence of mutation in number of cancer types \u2265 3 cancer types\n - Filter criteria 3 - Positive Patient's count \u2265 10 patients\n - Filter criteria 4 - Mutation reported and annotated in number of databases\n - Filter criteria 5 - Mutation minned from the literature using literaure mining tools (human_protein_mutation_literature.csv)\n - If there is also a germline mutation reported in dbSNP, the rsid is also shown\n - These filter criteria annotations are shown on the front end under the column Annotation Name\n - Also if the same mutation in the same cancer type on a given protein is reported in ICGC and TCGA then mutations from TCGA are only shown.\n - When mutations from TCGA are not available but are present in ICGC for the same protein and cancer type, ICGC mutations are shown in GlyGen\n - Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim.\n - On the GlyGen interface, in Mutations section the mutations that have passed highest number of filter criteria are displayed first irrespective of their amio acid positions. For eg. the mutation entry that has passed 5 filter criteria will be shown first.\n\nDescription Domain\n Keywords\n - single-nucleotide variations (nsSNVs)\n - cancer mutations\n - BioMuta\n - disease\n\n Pipeline Steps\n - Step-1: The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias\n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: mutid-map.final.csv\n URI: https://data.glygen.org/ln2wwwdata/source/mutid-map.final.csv\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Name: human_cancer_mutation_literature.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv\n Name: human_cancer_mutation_somatic.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_somatic.csv\n Name: human_cancer_mutation_literature.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv\n Output Subdomain\n Name: human_protein_mutation_cancer.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv\n Name: human_protein_mutation_cancer.stat.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"16\"\n Name: \"motif_start\"\n Description: \"\"\n Unique Values: \"23\"\n Name: \"filter_flags\"\n Description: \"Filter tags/flags assigned to the mutation entries that have passed the mutation filter criteria\"\n Unique Values: \"19\"\n Name: \"sift_prediction\"\n Description: \"The SIFT qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"3\"\n Name: \"somatic_status\"\n Description: \"The status of the variant whether it is germline (somatic status =0) or somatic (somatic status =1) variant\"\n Unique Values: \"1\"\n Name: \"chr_pos\"\n Description: \"Chromosome Position of a gene\"\n Unique Values: \"19\"\n Name: \"chr_id\"\n Description: \"\"\n Unique Values: \"10\"\n Name: \"dbsnp_id\"\n Description: \"\"A reference SNP ID number\"\n Unique Values: \"19\"\n Name: \"evidence_ECO:0000313\"\n Description: \"A type of evidence that is imported information used in an automatic assertion\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"19\"\n Name: \"mim_id\"\n Description: \"Disease ID from the OMIM database\"\n Unique Values: \"1\"\n Name: \"description\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"begin_aa_pos\"\n Description: \"Start position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"cytogenic_band\"\n Description: \"One of the subregions of a chromosome visible microscopically after special staining\"\n Unique Values: \"14\"\n Name: \"aa_pos\"\n Description: \"Position of the amino acid in canonical sequence of protein in the UniProtKB database\"\n Unique Values: \"18\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"9\"\n Name: \"sift_score\"\n Description: \"SIFT predicts whether an amino acid substitution is likely to affect protein function based on sequence homology and the physico-chemical similarity between the alternate amino acids. The data we provide for each amino acid substitution is a score and a qualitative prediction (either 'tolerated' or 'deleterious'). The score is the normalized probability that the amino acid change is tolerated so scores nearer zero are more likely to be deleterious. The qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"10\"\n Name: \"alt_motif\"\n Description: \"Altered motif\"\n Unique Values: \"24\"\n Name: \"disease_xrefs\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"polyphen_score\"\n Description: \"The score assigned to a amino acid substitution by a tool called as PolyPhen (=Polymorphism Phenotyping) which predicts possible impact of an amino acid substitution on the structure and function of a human protein using straightforward physical and comparative considerations. The PolyPhen score ranges from 0.0 (tolerated) to 1.0 (deleterious). Variants with scores of 0.0 are predicted to be benign. Values closer to 1.0 are more confidently predicted to be deleterious\"\n Unique Values: \"1\"\n Name: \"polyphen_prediction\"\n Description: \"\"The PolyPhen prediction values are - greater than 0.908 - \"\"Probably Damaging\"\"; greater than 0.446 and less than or equal to 0.908 - \"\"Possibly Damaging\"\"; less than or equal to 0.446 - \"\"Benign\"\"\"\n Unique Values: \"1\"\n Name: \"is_known_glycoprotein\"\n Description: \"Yes or no flag to denote if a protein is experimentally proven glycoprotein\"\n Unique Values: \"1\"\n Name: \"alt_nt\"\n Description: \"Alternative nucleotide\"\n Unique Values: \"1\"\n Name: \"protein_name\"\n Description: \"Protein name in the UniProtKB\"\n Unique Values: \"16\"\n Name: \"disease_evidence_ECO:0000313\"\n Description: \"The evidence that could be a PMID or a ClinVar ID that associates disease with the variant\"\n Unique Values: \"1\"\n Name: \"effect\"\n Description: \"The effect on glycosylation or N-sequon due to variation at site of glycosylated amino acid.\"\n Unique Values: \"3\"\n Name: \"end_aa_pos\"\n Description: \"End position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"mutation_type\"\n Description: \"Denotes whether mutation was reported with reference to amino acid or nucleotide\"\n Unique Values: \"1\"\n Name: \"disease_description\"\n Description: \"The disease description and/or definition \"\n Unique Values: \"1\"\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"1\"\n Name: \"evidence_ECO:0000269\"\n Description: \"A type of experimental evidence that is used in a manual assertion. Usually the values are PMIDs\"\n Unique Values: \"1\"\n Name: \"ref_nt\"\n Description: \"Reference nucleotide\"\n Unique Values: \"4\"\n Name: \"disease\"\n Description: \"The disease name for the cell line\"\n Unique Values: \"1\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"10\"\n Name: \"cosmic_id\"\n Description: \"Legacy mutation identifier (COSM) in Catalogue of Somatic Mutations in Cancer (COSMIC) represents existing COSM mutation identifiers. This identifier remains the same between different assemblies (GRCh37 and GRCh38). All the COSM ids at the same genomic location have been collapsed into one representative COSM id. These ids are maintained to help track existing mutations\"\n Unique Values: \"1\"\n Name: \"ref_motif\"\n Description: \"Reference motif\"\n Unique Values: \"20\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"minor_allelic_frequency\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"gene_name\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\"\n Unique Values: \"17\"\n Name: \"disease_evidence_ECO:0000269\"\n Description: \"The PMID evidence for the association of the disease with the variant.\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.11.2/reviewed/human_protein_mutation_cancer.csv" }